GR-ConvNet

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots2 results

Robotic GraspingonCornell Grasp Dataset
5 fold cross validation· 2019-09-11
97.7
best: 98.2 (grasp_det_seg_cnn (rgb only, IW split))
SOTA
Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network arXiv:1909.04810
Robotic Graspingon Jacquard dataset
Accuracy (%)· 2019-09-11
94.6
best: 95.6 (Efficient-Grasping)
SOTA
Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network arXiv:1909.04810